simulate_hardware_upgradeCompare le même profil avant et après une hausse de RAM ou VRAM. La simulation ne modifie rien et doit conclure qu'aucun achat n'est utile si le catalogue ne montre pas de gain.
| Name | Required | Description | Default |
|---|---|---|---|
| usage | No | polyvalent | |
| profile | Yes | ||
| target_ram_gb | No | ||
| target_vram_gb | No |
| Name | Required | Description | Default |
|---|---|---|---|
| decision | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description clearly states that the simulation is non-destructive ('ne modifie rien') and even reveals a potential outcome conclusion pattern, which goes well beyond the readOnlyHint annotation which only indicates it's read-only. No contradictions with annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences with no wasted words. It front-loads the purpose and follows with critical behavioral and usage guidelines. Every sentence earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the output schema exists and context signals show 4 parameters with one required, the description is complete. It explains what the tool does, how it works (non-destructive), and when to avoid using it. No gaps remain.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description must compensate. While the description doesn't detail each parameter, it references the core concepts of 'RAM ou VRAM' which map to 'target_ram_gb' and 'target_vram_gb', and 'profil' which maps to 'profile'. It also mentions 'usage' implicitly via context of comparing profiles. It adds functional meaning but could be more explicit about parameter roles.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb ('Compare') and resource ('profil avant et après une hausse de RAM ou VRAM'), making it clear what the tool does. It also helps distinguish this tool from siblings like 'check_pc_for_local_ai' by stating its comparative nature.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly states when not to use this tool ('ne modifie rien') and includes a conditional guideline ('doit conclure qu'aucun achat n'est utile si le catalogue ne montre pas de gain'), which helps the agent decide to call it only when confident a gain might exist.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool has a distinct purpose (analyze, check, explain, list, etc.) and the detailed descriptions make boundaries clear. However, the difference between 'reading a shared report' (analyze_shared_report) and 'reading a shared report to list installed models' (list_installed_models_from_report) or 'reading a shared report to list benchmarks' (list_benchmark_proofs_from_report) could cause an agent to pick the wrong one. There is also some overlap between these list operations that read a report versus simply displaying a pre-generated cockpit (render_machine_cockpit).
The majority of tools follow a consistent verb_noun pattern (e.g., analyze_shared_report, explain_bottleneck, list_installed_models_from_report, recommend_runtime). Minor inconsistency exists with the use of 'geo_audit' vs 'geo_kit' vs 'ratings' and the verb tense in 'list_benchmark_proofs_from_report' and 'list_first_party_measurements' departs from a simple pattern.
15 tools is at the high end of the ideal range (3-15), but each tool appears justified given the comprehensive scope of local AI assistance (hardware checking, model lookup, benchmarking, reporting, educational/reference tools). Slightly over-stuffed but still manageable for an agent.
The surface covers a complete workflow: check hardware, lookup models, benchmark, generate cockpit, explain bottlenecks, simulate upgrades, and reference documentation. The missing piece is the lack of 'update' or 'delete' operations, but this is by design, as the entire workflow is read-only. The set seems like a complete view of all possible read-only interactions with the domain.